verify

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and largely does: it discloses that GET avoids a refetch, that fresh checks are rate-limited, that local:true executes the bundled verify-ref.cjs on the caller's machine instead of Peerkith, and that ok:true only holds for the 'verified' tier. It stops short of describing auth requirements or the shape of the returned verdict.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely dense and front-loaded — the two input→behavior mappings come first, then local execution, then the ok:true invariant. Nothing is padding, but the telegraphic brace syntax and slash-heavy sentences push it toward cryptic rather than clean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 6-parameter, 0-required tool with no output schema and no annotations, the description covers routing, one side-effect, and the ok:true invariant, but never sketches what a verdict response contains or how failures are surfaced. Adequate to invoke, incomplete to interpret.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 17%, so the description must compensate, and it does: row is tied to the stored-verdict path, card+job+proof to the fresh-check path, and local to the reference-verifier path. 'fresh' semantics are covered by the schema itself. Minor gap: 'card', 'job' and 'proof' formats are never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb (check/verify) mapped to two distinct input shapes, each with its own route (GET for stored verdict vs POST for fresh check). An agent can tell the two modes apart, though domain nouns like 'row', 'card', 'job' and 'Peerkith' are used without definition, and no sibling (e.g. cap_check) is named for contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Routing conditions are explicit: pass a row to get the stored verdict without refetch, pass {card, job, proof} for a fresh check, and proof alone yields ok:false with a stated reason. It also flags local:true as a substitute execution path. What's missing is guidance on when to prefer this over the capability siblings (cap_check, cap_preflight).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.